TSrepr (version 1.0.4)

repr_feaclip: FeaClip representation of time series

Description

The repr_feaclip computes representation of time series based on feature extraction from bit-level (clipped) representation.

Usage

repr_feaclip(x)

Arguments

x

the numeric vector (time series)

Value

the numeric vector of length 8

Details

FeaClip is method of time series representation based on feature extraction from run lengths (RLE) of bit-level (clipped) representation. It extracts 8 key features from clipped representation.

There are as follows: $$repr = \{ max_1 - max. from run lengths of ones,$$ $$sum_1 - sum of run lengths of ones,$$ $$max_0 - max. from run lengths of zeros,$$ $$crossings - length of RLE encoding - 1,$$ $$f_0 - number of first zeros,$$ $$l_0 - number of last zeros,$$ $$f_1 - number of first ones,$$ $$l_1 - number of last ones \} .$$

References

Laurinec P, and Lucka M (2018) Interpretable multiple data streams clustering with clipped streams representation for the improvement of electricity consumption forecasting. Data Mining and Knowledge Discovery. Springer. DOI: 10.1007/s10618-018-0598-2

See Also

repr_featrend, repr_feacliptrend

Examples

# NOT RUN {
repr_feaclip(rnorm(50))

# }